基于神经网络的铀矿国际市场价格预测
|
摘要
人工神经网络是一门新兴的边缘科学,是模拟人脑智能结构和功能而开发出来的非线性信息处理系统,具有学习能力、并行性、容错性及易于硬件实现等基本特征,主要用于解决模式分类、函数逼近和数据压缩三大问题。近二十年来,神经网络在价格预测领域得到了广泛的应用。
铀矿市场是一个高度复杂的非线性动态系统,其变化规律即有一定的自身趋势性,又受经济、政治等诸多因素的影响。传统的定量预测方法在研究铀矿价格预测时面临着许多困难。因神经网络具有自组织、自适应等特点,能自动从历史数据中发掘有关价格变化的知识,因而非常适用于解决铀矿价格预测问题。然而,迄今为止,这样的预测模型在国内外还未见报道。本文的主要工作包括以下几个方面：
(1)简要分析了铀矿价格的影响因素,应用神经网络的原理,采用多输入、单隐层和单输出系统,建立了国际市场铀矿价格的神经网络预测模型,并对其未来五个月的变化进行了预测；
(2)研究了BP神经网络在MATLAB中的设计与实现,以及如何在MATLAB中创建BP神经网络,如何对网络进行初始化、训练和模拟,介绍了本文经常用到的一些MATLAB函数,并采用MATLAB编程实现了所设计的BP网络；
(3)对铀矿价格进行了实例预测研究,研究结果表明,预测结果的精度较高,证明了本文所采用的研究方法是实用而有效的,验证了本文所建立的基于BP神经网络的铀矿价格预测模型的有效性和适用性。
The artificial neural networks is a newly developed interdisciplinary. It is a non-linear information processing system to imitate the structure and function of human brain.It possesses learning ability, parallelism, robustness and easiness for hardware implementation. It mainly applies to pattern classification, function approximation and date compression. Neural networks have developed rapidly in the past twenty years and have got a wide application in the fields of price prediction.
Uranium price market is a highly complicate nonlinear system, whose variation does not have its own regulation, but also is influenced by many other factors, such as politics and economy. The tradition prediction techniques based on statistics face difficulties in uranium price research. Neural network have the virtue of self-organization and adaptability and can excavate the valuable information from historical data. So it is suitable to solve the problem in uranium price prediction.However, by now, researches did not established the relevant prediction models for uranium price at present. The paper mainly includes the following works:
(1)The paper briefy introduces some basic knowledge on neural network and effected factors of uranium price. Using single hidden layer and multiple output system, a BP network model was built up to forecast the trend of uranium price in the next five months;
(2)The paper briefy introduces how to realize BP neural network in MATLAB,how to create, initiate, train and simulate a network and some functions usually used in MATLAB.And a program is written to realize the BP network;
(3)The paper does a experiment on the uranium price in the recent twenty years.,proves that the model and research method is effective.Compared with the prediction results, the results is briefly accepted, demonstrating that the forecasting model based on BP network has a good ability to forecast and generalize.
铀矿市场是一个高度复杂的非线性动态系统,其变化规律即有一定的自身趋势性,又受经济、政治等诸多因素的影响。传统的定量预测方法在研究铀矿价格预测时面临着许多困难。因神经网络具有自组织、自适应等特点,能自动从历史数据中发掘有关价格变化的知识,因而非常适用于解决铀矿价格预测问题。然而,迄今为止,这样的预测模型在国内外还未见报道。本文的主要工作包括以下几个方面：
(1)简要分析了铀矿价格的影响因素,应用神经网络的原理,采用多输入、单隐层和单输出系统,建立了国际市场铀矿价格的神经网络预测模型,并对其未来五个月的变化进行了预测；
(2)研究了BP神经网络在MATLAB中的设计与实现,以及如何在MATLAB中创建BP神经网络,如何对网络进行初始化、训练和模拟,介绍了本文经常用到的一些MATLAB函数,并采用MATLAB编程实现了所设计的BP网络；
(3)对铀矿价格进行了实例预测研究,研究结果表明,预测结果的精度较高,证明了本文所采用的研究方法是实用而有效的,验证了本文所建立的基于BP神经网络的铀矿价格预测模型的有效性和适用性。
The artificial neural networks is a newly developed interdisciplinary. It is a non-linear information processing system to imitate the structure and function of human brain.It possesses learning ability, parallelism, robustness and easiness for hardware implementation. It mainly applies to pattern classification, function approximation and date compression. Neural networks have developed rapidly in the past twenty years and have got a wide application in the fields of price prediction.
Uranium price market is a highly complicate nonlinear system, whose variation does not have its own regulation, but also is influenced by many other factors, such as politics and economy. The tradition prediction techniques based on statistics face difficulties in uranium price research. Neural network have the virtue of self-organization and adaptability and can excavate the valuable information from historical data. So it is suitable to solve the problem in uranium price prediction.However, by now, researches did not established the relevant prediction models for uranium price at present. The paper mainly includes the following works:
(1)The paper briefy introduces some basic knowledge on neural network and effected factors of uranium price. Using single hidden layer and multiple output system, a BP network model was built up to forecast the trend of uranium price in the next five months;
(2)The paper briefy introduces how to realize BP neural network in MATLAB,how to create, initiate, train and simulate a network and some functions usually used in MATLAB.And a program is written to realize the BP network;
(3)The paper does a experiment on the uranium price in the recent twenty years.,proves that the model and research method is effective.Compared with the prediction results, the results is briefly accepted, demonstrating that the forecasting model based on BP network has a good ability to forecast and generalize.
引文
[1]Kimoto, T&Asakawa K.Stock. Market Prediction System with Modular Neural Netw orks[J].Proceeding of the International Joint Conference on Neural Networks.1990, 1:1-6.
[2]Chen, C.H, Neural networks for financial market prediction[J].IEEE World Congres s on Computational In telligence.,1994,2(27):1199-1202.
[3]丁雪梅.基于BP算法的证券预测技术研究[D].重庆：重庆大学,2002.
[4]Lapeds.A, Farber. Genetic Data Base Analysis with Neural Networks. Neural Infor-mation[J].Processing System-Nature and Synthetic.2002,2(10):124-127.
[5]张建国,孟晋.世界铀资源、生产、供应与需求的新动态[J].铀矿冶,2006,25(1)：21-28.
[6]朱大奇,史慧.人工神经网络原理及应用[M].北京：科学出版社,2006.
[7]J.J.Hopfield. Neural with Grad Response have collective Computational properties li ke those of two state neurons[J].Proc.Nati.Acad.1984,81:3092-3099.
[8]Lapeds.A, Farber. Genetic Data Base Analysis with Neural Networks. Neural Inform ation[J].Processing System-Nature and Synthetic.2002,2(10):1022-1025.
[9]陈鸿.人工神经网络在宏观经济预测中的应用研究[D].重庆：重庆大学,2005.
[10]Tung Bui, Jintae Lee. An agent-based frame work for building decision support sy-stems[J].Decision Support System.1999,25(3):43-47.
[11]Leonardo J, Tashman, Michael. E.Software review[J].International Journal of Foreca sting.1993,9(3):32-37.
[12]M.A.H.Dempster, A.M.Ireland. Object oriented model integration in a financial decis ion support system[J].Decision Support Systems.1991,7(4):67-69.
[13]Peter McAdam, Paul McNelis. Forecasting inflation with thick models and neural n etworks[J].Economic Modelling,22(2005):848-867
[14]Philip Tsang, Paul Kwok, S Choy. Design and implementation of NN5 for Hong K ong stock price forecasting[J].Engineering Applications of Artificial Intelligence,20 (2007):453-461
[15]Antonino Parisi, Franco Parisi, David Diaz. Forecasting gold price changes:rolling and recursive neural network models[J].J. of Multi. Fin. Manag.,18(2008):477-487
[16]CosBkun Hamzacebi. Improving artificial neural networks' performance in seasonal ti me series forecasting[J].Information Sciences,178(2008):4550-4559
[17]Lean Yu, Shouyang Wang, Kin Keung Lai.A neural-network-based nonlinear metam odeling approach to financial time series forecasting[J].Applied Soft Computing,9 (2009):563-574
[18]Zong Woo Geem, William E Roper. Energy demand estimation of South Korea usin g artificial neural network[J].Energy Policy,37(2009):4049-4054
[19]常引.基于BP神经网络的陕西省农民收入预测研究[D].西安：西北农林科技大学,2008.
[20]李建华.基于BP神经网络的二手船船价指数预测研究[D].大连：大连海事大学,2008.
[21]钱竹,石殿瑜,徐鹏等.BP神经网络在协定法麦汗理化指标预测中的应用[J].酿酒科技,2008,4(1)：54-56.
[22]苏变萍,王一平.基于BP神经网络的信息商品价格预测模型[J].统计与信息论坛,2007,22(1)：93-95.
[23]于海燕.基于模型神经网络的电力负荷短期预测[D].天津：天津大学,2007.
[24]陈鸿.人工神经网络在宏观经济预测中的应用研究[D].重庆：重庆大学,2005.
[25]王东旭.一种基于人工神经网络的短期股价预测模型的研究[D].天津：天津工业大学,2006.
[26]顾军华,宋丽娟等.基于改进BP神经网络的税收收入预测模型[J].河北：河北工业大学学报,2003：02-07.
[27]刘艳荣.基于BP网络的彩票预测系统的研究[D].天津：天津大学,2006.
[28]张建国.中国铀矿开采技术特点及发展水平[J].世界核地质科学,2007,24(4)：153-155.
[29]蒋振频,管太阳,吴雅梅.2006年国际铀价回顾与铀价预测分析[J].世界核地质科学,2007,24(4)：153-155
[30]s.n. Canada's uranium production & nuclear power[EB/OL].http://www.uic.com.au/ni p03.htm,2007.
[31]许东.基于MATLAB6.x的系统分析与设计—神经网络[M].西安：电子科技大学出版社,2002.
[32]李开文.中国铀矿开采技术特点及发展水平[J].中国矿业,2002,11(1)：23-27.
[33]Rumelhart C.E, H.GE.,Williams R.J. learning internal representations by error prop agation in Parallel Distributed[J].Proeessing MIT Press.1986:318-362.
[34]Churing Y.Baekprogation. Theory, Architecture and Application. NewYork[M].Lawr ence Erbaum Publisher,1995.
[35]Hornik K M,Stinchcombe M, White H.Multilayer. Feedforward networks are univer sal approximators[J].Neural allel DisNetworks,1989,2(2):359-366.
[36]孙增沂等.智能控制理论与技术[M].北京：清华大学出版社,1997.
[37]倪红梅,王维刚,罗仕明.人工神经网络在采油产量预测中的应用[J].陕西理工学院学报(自然科学版),2008,24(3)：36-40.
[38]陈光华.人工神经网络在证券价格预测中的应用[J].计算机仿真,2007,24(10)：244-248.
[39]葛哲学,孙志强.神经网络理论与MATLABR2007实现[M].北京：电子工业出版社,2007.
[40]Bianchini M, Frasconi P. Cori M. Learning without Local Minima in Radial Basis Function Network[J].IEEE Transactions On Neural Network.1995,6(3):749-756.
[41]秦伟刚.基于人工神经网络的智能交通系统检测与控制[D].济南：山东大学,2005.
[42]闵惜琳.用MATLAB神经网络工具箱开发BP网络应用[J].计算机应用,2001,21(8)：163-164.
[43]丛爽.面向MATLAB工具箱的网络理论与应用(第二版)[M].中国科学科技大学出版社,2005.
[44]王继成.一种新的网络学习算法[J].计算机工程与科学,2000,22(3)：6-11.
[45]王继成.基于神经网络的我国上市公司财务危机预测的实证研究[D].杭州：浙江大学,2005
[46]乐菲菲,马力.基于层次分析法的主观概率设定法[J].统计与决策,2006,1(22)：37-38.
[47]张灿鹏,郭砚常.市场调查与分析预测[J].北京：清华大学出版社,2008.
[48]徐龙封,朱文刚.对集体经验判断预测法的新构想[J]..华东冶金冶金学院学报,2000,17(4)：365-369.
[49]刘洪波,尹永刚,黄树军等.情景分析法在工业园区水环境影响预测评价中的应用[J].中国科技信息,2006,2(24)：23-24.
[50]高峻峻,谭崇利,刘悦.一类产品需求预测的支持向量机方法[J].上海大学学报(自然科学版),2009,15(1)：71-76.
[51]王波.基于神经网络的金融时间序列分析[D].天津：天津大学,2005.
[52]陆青翠.基于回归分析法的工程企业成本价的计算[J].福州大学学报(哲学社会科学版),2008,4(6)：23-27.
[53]牛东晓,李春祥,孟明.基于灰色和偏最小二乘方法的年度负荷预测[J].华东电力,2009,37(6)：0989-0992.
[54]张晓红.神经网络经济预测法研究[J].预测,2001,7(6)：61-63.
[55]周靖.随机时间序列模型在商品国际价格预测中的适用性研究[D].成都：西南财经大学,2007.
[56]蒋白懿,代进,高金良.城市日用水量预测模型比较研究[J].学院建筑大学学报,2008,24(2)：278-281.
[57]王玉明,李娟生,刘建地.自回归滑动平均混合模型在甘肃省麻疹发病预测中的应用[J].中国疫苗和免疫,2008,14(6)：512-515.
[58]黎曦,胡奎,胡伍生.神经网络BP算法在工程估价中的运用[J].山西建筑,2007,33(28)：367-368.
[59]周开利,康耀红.神经网络模型及其MATTLAB仿真程序—设计[M].北京：清华大学出版社,2005
[60]钟义信等.智能理论与技术—人工智能与神经网络[M].北京：人民邮电出版社,1992.
[61]侯君,姚志红.基于BP神经网络的湖泊水体富营养化的矩短期预测[J].实验室研究与探索,2008,27(6)：38-40.
[62]樊俊谦.论基于BP神经网络的GDP预测[J].总裁,2009,2(3)：59-61.
[63]高隽.人工神经网络原理及仿真实例[M].北京：北京机械工业出版社,2003.
[64]Granion A.Korn. Neural Networks and Fuzzy-Logic Control on Personal Computers and Workstations[M],MIT Press,1995.
[65]闻新,周露,王丹力等.MALTAB神经网络应用设计[M].北京：科学出版社,2001.
[66]祁庆钦.基于神经网络的人工林油松木材径向解剖特性预测研究[D].呼和浩特：内蒙古农业大学,2008.
[67]汪荣鑫.随机过程[M].西安：西安交通大学出版社,2004.
[68]邓聚龙.灰预测与灰决策[M].武汉：华中科技大学出版社,2002.
[69]李涛,贺勇军,刘志剑.Matlab工具箱应用指南[M].北京：电子工业出版社,2000.
[70]戚德虎,康继昌.BP神经网络的设计[J].计算机工程与设计,1998,2(6)：38-43.
[71]姚培福.人工神经网络在股票预测中的应用与研究[D].昆明：昆明理工大学,2007.
[2]Chen, C.H, Neural networks for financial market prediction[J].IEEE World Congres s on Computational In telligence.,1994,2(27):1199-1202.
[3]丁雪梅.基于BP算法的证券预测技术研究[D].重庆：重庆大学,2002.
[4]Lapeds.A, Farber. Genetic Data Base Analysis with Neural Networks. Neural Infor-mation[J].Processing System-Nature and Synthetic.2002,2(10):124-127.
[5]张建国,孟晋.世界铀资源、生产、供应与需求的新动态[J].铀矿冶,2006,25(1)：21-28.
[6]朱大奇,史慧.人工神经网络原理及应用[M].北京：科学出版社,2006.
[7]J.J.Hopfield. Neural with Grad Response have collective Computational properties li ke those of two state neurons[J].Proc.Nati.Acad.1984,81:3092-3099.
[8]Lapeds.A, Farber. Genetic Data Base Analysis with Neural Networks. Neural Inform ation[J].Processing System-Nature and Synthetic.2002,2(10):1022-1025.
[9]陈鸿.人工神经网络在宏观经济预测中的应用研究[D].重庆：重庆大学,2005.
[10]Tung Bui, Jintae Lee. An agent-based frame work for building decision support sy-stems[J].Decision Support System.1999,25(3):43-47.
[11]Leonardo J, Tashman, Michael. E.Software review[J].International Journal of Foreca sting.1993,9(3):32-37.
[12]M.A.H.Dempster, A.M.Ireland. Object oriented model integration in a financial decis ion support system[J].Decision Support Systems.1991,7(4):67-69.
[13]Peter McAdam, Paul McNelis. Forecasting inflation with thick models and neural n etworks[J].Economic Modelling,22(2005):848-867
[14]Philip Tsang, Paul Kwok, S Choy. Design and implementation of NN5 for Hong K ong stock price forecasting[J].Engineering Applications of Artificial Intelligence,20 (2007):453-461
[15]Antonino Parisi, Franco Parisi, David Diaz. Forecasting gold price changes:rolling and recursive neural network models[J].J. of Multi. Fin. Manag.,18(2008):477-487
[16]CosBkun Hamzacebi. Improving artificial neural networks' performance in seasonal ti me series forecasting[J].Information Sciences,178(2008):4550-4559
[17]Lean Yu, Shouyang Wang, Kin Keung Lai.A neural-network-based nonlinear metam odeling approach to financial time series forecasting[J].Applied Soft Computing,9 (2009):563-574
[18]Zong Woo Geem, William E Roper. Energy demand estimation of South Korea usin g artificial neural network[J].Energy Policy,37(2009):4049-4054
[19]常引.基于BP神经网络的陕西省农民收入预测研究[D].西安：西北农林科技大学,2008.
[20]李建华.基于BP神经网络的二手船船价指数预测研究[D].大连：大连海事大学,2008.
[21]钱竹,石殿瑜,徐鹏等.BP神经网络在协定法麦汗理化指标预测中的应用[J].酿酒科技,2008,4(1)：54-56.
[22]苏变萍,王一平.基于BP神经网络的信息商品价格预测模型[J].统计与信息论坛,2007,22(1)：93-95.
[23]于海燕.基于模型神经网络的电力负荷短期预测[D].天津：天津大学,2007.
[24]陈鸿.人工神经网络在宏观经济预测中的应用研究[D].重庆：重庆大学,2005.
[25]王东旭.一种基于人工神经网络的短期股价预测模型的研究[D].天津：天津工业大学,2006.
[26]顾军华,宋丽娟等.基于改进BP神经网络的税收收入预测模型[J].河北：河北工业大学学报,2003：02-07.
[27]刘艳荣.基于BP网络的彩票预测系统的研究[D].天津：天津大学,2006.
[28]张建国.中国铀矿开采技术特点及发展水平[J].世界核地质科学,2007,24(4)：153-155.
[29]蒋振频,管太阳,吴雅梅.2006年国际铀价回顾与铀价预测分析[J].世界核地质科学,2007,24(4)：153-155
[30]s.n. Canada's uranium production & nuclear power[EB/OL].http://www.uic.com.au/ni p03.htm,2007.
[31]许东.基于MATLAB6.x的系统分析与设计—神经网络[M].西安：电子科技大学出版社,2002.
[32]李开文.中国铀矿开采技术特点及发展水平[J].中国矿业,2002,11(1)：23-27.
[33]Rumelhart C.E, H.GE.,Williams R.J. learning internal representations by error prop agation in Parallel Distributed[J].Proeessing MIT Press.1986:318-362.
[34]Churing Y.Baekprogation. Theory, Architecture and Application. NewYork[M].Lawr ence Erbaum Publisher,1995.
[35]Hornik K M,Stinchcombe M, White H.Multilayer. Feedforward networks are univer sal approximators[J].Neural allel DisNetworks,1989,2(2):359-366.
[36]孙增沂等.智能控制理论与技术[M].北京：清华大学出版社,1997.
[37]倪红梅,王维刚,罗仕明.人工神经网络在采油产量预测中的应用[J].陕西理工学院学报(自然科学版),2008,24(3)：36-40.
[38]陈光华.人工神经网络在证券价格预测中的应用[J].计算机仿真,2007,24(10)：244-248.
[39]葛哲学,孙志强.神经网络理论与MATLABR2007实现[M].北京：电子工业出版社,2007.
[40]Bianchini M, Frasconi P. Cori M. Learning without Local Minima in Radial Basis Function Network[J].IEEE Transactions On Neural Network.1995,6(3):749-756.
[41]秦伟刚.基于人工神经网络的智能交通系统检测与控制[D].济南：山东大学,2005.
[42]闵惜琳.用MATLAB神经网络工具箱开发BP网络应用[J].计算机应用,2001,21(8)：163-164.
[43]丛爽.面向MATLAB工具箱的网络理论与应用(第二版)[M].中国科学科技大学出版社,2005.
[44]王继成.一种新的网络学习算法[J].计算机工程与科学,2000,22(3)：6-11.
[45]王继成.基于神经网络的我国上市公司财务危机预测的实证研究[D].杭州：浙江大学,2005
[46]乐菲菲,马力.基于层次分析法的主观概率设定法[J].统计与决策,2006,1(22)：37-38.
[47]张灿鹏,郭砚常.市场调查与分析预测[J].北京：清华大学出版社,2008.
[48]徐龙封,朱文刚.对集体经验判断预测法的新构想[J]..华东冶金冶金学院学报,2000,17(4)：365-369.
[49]刘洪波,尹永刚,黄树军等.情景分析法在工业园区水环境影响预测评价中的应用[J].中国科技信息,2006,2(24)：23-24.
[50]高峻峻,谭崇利,刘悦.一类产品需求预测的支持向量机方法[J].上海大学学报(自然科学版),2009,15(1)：71-76.
[51]王波.基于神经网络的金融时间序列分析[D].天津：天津大学,2005.
[52]陆青翠.基于回归分析法的工程企业成本价的计算[J].福州大学学报(哲学社会科学版),2008,4(6)：23-27.
[53]牛东晓,李春祥,孟明.基于灰色和偏最小二乘方法的年度负荷预测[J].华东电力,2009,37(6)：0989-0992.
[54]张晓红.神经网络经济预测法研究[J].预测,2001,7(6)：61-63.
[55]周靖.随机时间序列模型在商品国际价格预测中的适用性研究[D].成都：西南财经大学,2007.
[56]蒋白懿,代进,高金良.城市日用水量预测模型比较研究[J].学院建筑大学学报,2008,24(2)：278-281.
[57]王玉明,李娟生,刘建地.自回归滑动平均混合模型在甘肃省麻疹发病预测中的应用[J].中国疫苗和免疫,2008,14(6)：512-515.
[58]黎曦,胡奎,胡伍生.神经网络BP算法在工程估价中的运用[J].山西建筑,2007,33(28)：367-368.
[59]周开利,康耀红.神经网络模型及其MATTLAB仿真程序—设计[M].北京：清华大学出版社,2005
[60]钟义信等.智能理论与技术—人工智能与神经网络[M].北京：人民邮电出版社,1992.
[61]侯君,姚志红.基于BP神经网络的湖泊水体富营养化的矩短期预测[J].实验室研究与探索,2008,27(6)：38-40.
[62]樊俊谦.论基于BP神经网络的GDP预测[J].总裁,2009,2(3)：59-61.
[63]高隽.人工神经网络原理及仿真实例[M].北京：北京机械工业出版社,2003.
[64]Granion A.Korn. Neural Networks and Fuzzy-Logic Control on Personal Computers and Workstations[M],MIT Press,1995.
[65]闻新,周露,王丹力等.MALTAB神经网络应用设计[M].北京：科学出版社,2001.
[66]祁庆钦.基于神经网络的人工林油松木材径向解剖特性预测研究[D].呼和浩特：内蒙古农业大学,2008.
[67]汪荣鑫.随机过程[M].西安：西安交通大学出版社,2004.
[68]邓聚龙.灰预测与灰决策[M].武汉：华中科技大学出版社,2002.
[69]李涛,贺勇军,刘志剑.Matlab工具箱应用指南[M].北京：电子工业出版社,2000.
[70]戚德虎,康继昌.BP神经网络的设计[J].计算机工程与设计,1998,2(6)：38-43.
[71]姚培福.人工神经网络在股票预测中的应用与研究[D].昆明：昆明理工大学,2007.